Ground-penetrating radar (GPR) is an important geophysical technique in subsurface detection. However, traditional numerical simulation methods such as finite-difference time-domain (FDTD) face challenges in accurately simulating complex heterogeneous mediums in real-world scenarios due to the difficulty of obtaining precise medium distribution information and high computational costs. Meanwhile, deep learning methods require excessive prior information, which limits their application. To address these issues, this paper proposes a novel two-step forward modeling strategy for GPR data of metal pipes. The first step employs the proposed Polarization Self-Attention Image Translation network (PSA-ITnet) for image translation, which is inspired by the process where a neural network model “understands” image content and “rewrites” it according to specified rules. It converts scene layout images (cross-sectional schematics depicting geometric details such as the size and spatial distribution of underground buried metal pipes and their surrounding medium) into simulated clutter-free GPR B-scan images. By integrating the polarized self-attention (PSA) mechanism into the Unet generator, PSA-ITnet can capture long-range dependencies, enhancing its understanding of the longitudinal time-delay property in GPR B-scan images. which is crucial for accurately generating hyperbolic signatures of metal pipes in simulated data. The second step uses the Polarization Self-Attention Style Transfer network (PSA-STnet) for style transfer, which transforms the simulated clutter-free images into data matching the distribution and characteristics of a real-world underground heterogeneous medium under unsupervised conditions while retaining target information. This step bridges the gap between ideal simulations and actual GPR data. Simulation experiments confirm that PSA-ITnet outperforms traditional methods in image translation, and PSA-STnet shows superiority in style transfer. Real-world experiments in a complex bridge support structure scenario further verify the method’s practicability and robustness. Compared to FDTD, the proposed strategy is capable of generating GPR data matching real-world subsurface heterogeneous medium distributions from scene layout models, significantly reducing time costs and providing an efficient solution for GPR data simulation and analysis.

The propagation of electromagnetic waves underground is subject to the heterogeneity of the medium and exceedingly complex. In Ground Penetrating Radar (GPR) images with metal pipe targets, distinguishing target information clearly while decluttering interference under unsupervised conditions poses a significant challenge. Previous methods primarily leverage subspace method to decompose echo data into target and clutter information. However, due to the strong coupling of target and clutter signals in both time and frequency domains, effective separation remains difficult. To address this issue, this paper proposes an unsupervised multi-attention domain adaptive model (UMDA-net) capable of transforming targets from domains with complex clutter to domains with clean backgrounds. The overall structure consists of two U-net-based generators and a discriminator, guided by adversarial loss and consistency loss functions during training. Furthermore, multiple attention mechanisms, such as channel attention (CA), spatial attention (SA), and multi-heads self-attention (MSA), are integrated into the generators, enhancing semantic discrimination capability and suppressing clutter information similar to target echoes. Finally, both simulation and real-world experiments validate the effectiveness of the proposed model, and ablation studies demonstrate the contributions of each attention mechanism in clutter suppression. This research provides a effective solution for processing GPR images with metal pipe targets under unsupervised conditions.

The target detection task of ground penetrating radar (GPR) based on deep learning has received widespread attention. Previous studies focused more on the features of targets in images and achieved excellent performance. However, in the practical application of these methods, GPR image is cut into several slices for feeding to the model for training and inference, which not only requires accumulating pulses, but disrupts the continuity of pulse information, making it difficult to communicate semantic information of different parts of the same pulse in different slices. To address these issues, this letter proposes a pulse-by-pulse target detection model, namely 1D Mix Attention (MA) TransUnet, for GPR, avoiding pulse accumulation and preserving the continuity of pulse information. In structure, the spatial and channel mixed attention mechanism replaces skip connections in 1D Unet, which effectively enhances the target features in pulse data. In addition, Transformer block based on Multi-head Self Attention (MSA) is applied to the downsampling feature map of 1D Unet, which allows the model to effectively understand the global semantic information and suppress non target features that are similar to the target features in pulse data. Finally, the effectiveness of 1D MA TransUnet is validated using GPR pulse data containing steel mesh as a case study. The model achieved an accuracy of 83.07%, a recall rate of 71.64%, and an F1 score of 76.93%, respectively.